Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2528 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.9523. Min Act: -0.0002
Data Index: 367195 (The Pile)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.9514. Min Act: -0.0002
Data Index: 949820 (The Pile)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0077. Min Range: -1.0077
Max Act: 1.0077. Min Act: -0.0002
Data Index: 939358 (The Pile)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.9536. Min Act: -0.0002
Data Index: 6261 (The Pile)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.9013. Min Act: -0.0002
Data Index: 1811461 (The Pile)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.9300. Min Act: -0.0002
Data Index: 585684 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.8963. Min Act: -0.0002
Data Index: 1978124 (The Pile)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.8607. Min Act: -0.0002
Data Index: 113778 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.8663. Min Act: -0.0002
Data Index: 1013850 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.8499. Min Act: -0.0002
Data Index: 1379242 (The Pile)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.8765. Min Act: -0.0002
Data Index: 923880 (The Pile)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.8840. Min Act: -0.0002
Data Index: 1718615 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.8731. Min Act: -0.0002
Data Index: 625824 (The Pile)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.8971. Min Act: -0.0002
Data Index: 101524 (The Pile)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.8207. Min Act: -0.0002
Data Index: 1596930 (The Pile)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.8466. Min Act: -0.0002
Data Index: 365989 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.7870. Min Act: -0.0002
Data Index: 36552 (The Pile)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.8135. Min Act: -0.0002
Data Index: 1986229 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.7628. Min Act: -0.0002
Data Index: 527195 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0077. Min Range: -1.0077
Max Act: 0.7554. Min Act: -0.0002
Data Index: 562793 (The Pile)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19